Search Results for author:
Found 47 papers, 23 papers with code
Event Extraction as Machine Reading Comprehension
ii) Our model is excelled in the data-scarce scenario, for example, obtaining 49. 8{\%} in F1 for event argument extraction with only 1{\%} data, compared with 2. 2{\%} of the previous method.
On Synthetic Data for Back Translation
Back translation (BT) is one of the most significant technologies in NMT research fields.
Set Generation Networks for End-to-End Knowledge Base Population
In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts.
A Benchmark for Text Expansion: Datasets, Metrics, and Baselines
This work presents a new task of Text Expansion (TE), which aims to insert fine-grained modifiers into proper locations of the plain text to concretize or vivify human writings.
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge.
Explicit Syntactic Guidance for Neural Text Generation
Most existing text generation models follow the sequence-to-sequence paradigm.
Pre-training Multi-party Dialogue Models with Latent Discourse Inference
Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows.
A Frustratingly Simple Decoding Method for Neural Text Generation
We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation.
Deepfake Text Detection in the Wild
In practical scenarios, the detector faces texts from various domains or LLMs without knowing their sources.
Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance
ChatGPT and GPT-4 have attracted substantial interest from both academic and industrial circles, owing to their remarkable few-shot (or even zero-shot) ability to handle various tasks.
Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog
Retrieving proper domain knowledge from an external database lies at the heart of end-to-end task-oriented dialog systems to generate informative responses.
Explanation Regeneration via Information Bottleneck
Explaining the black-box predictions of NLP models naturally and accurately is an important open problem in natural language generation.
Effidit: Your AI Writing Assistant
In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME).
Spatial Entropy as an Inductive Bias for Vision Transformers
In this work, we propose a different and complementary direction, in which a local bias is introduced using an auxiliary self-supervised task, performed jointly with standard supervised training.
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
In particular, MJP first shuffles the selected patches via our block-wise random jigsaw puzzle shuffle algorithm, and their corresponding PEs are occluded.
Lexical Knowledge Internalization for Neural Dialog Generation
We propose knowledge internalization (KI), which aims to complement the lexical knowledge into neural dialog models.
A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation
To alleviate the above data issues, we propose a data manipulation method, which is model-agnostic to be packed with any persona-based dialogue generation model to improve its performance.
Event Transition Planning for Open-ended Text Generation
Open-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context.
Efficient Training of Visual Transformers with Small Datasets
This task encourages the VTs to learn spatial relations within an image and makes the VT training much more robust when training data are scarce.
Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information.
REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation
We first clarify an assumption on reference-based metrics that, if more high-quality references are added into the reference set, the reliability of the metric will increase.
Data Augmentation for Text Generation Without Any Augmented Data
Data augmentation is an effective way to improve the performance of many neural text generation models.
Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
The task requires models to generate personalized responses for a speaker given a few conversations from the speaker and a social network.
Predicting Events in MOBA Games: Prediction, Attribution, and Evaluation
The multiplayer online battle arena (MOBA) games have become increasingly popular in recent years.
Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems
To conquer these limitations, we propose a Dual Dynamic Memory Network (DDMN) for multi-turn dialog generation, which maintains two core components: dialog memory manager and KB memory manager.
TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching
Although neural table-to-text models have achieved remarkable progress with the help of large-scale datasets, they suffer insufficient learning problem with limited training data.
Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification
Neural table-to-text models, which select and order salient data, as well as verbalizing them fluently via surface realization, have achieved promising progress.
Pretrained Language Models for Dialogue Generation with Multiple Input Sources
In this work, we study dialogue models with multiple input sources adapted from the pretrained language model GPT2.
Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning
Besides a small number of high-resource sentence functions, a large portion of sentence functions is infrequent.
Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
In previous work, the external document is utilized by (1) creating a context-aware document memory that integrates information from the document and the conversational context, and then (2) generating responses referring to the memory.
A Batch Normalized Inference Network Keeps the KL Vanishing Away
Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks.
Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation
In this paper, we focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer and aims to preserve text styles while altering the content.
Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation.
Relevance-Promoting Language Model for Short-Text Conversation
In this paper, we propose to formulate the STC task as a language modeling problem and tailor-make a training strategy to adapt a language model for response generation.
A Discrete CVAE for Response Generation on Short-Text Conversation
In this paper, we introduce a discrete latent variable with an explicit semantic meaning to improve the CVAE on short-text conversation.
Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework
End-to-end sequence generation is a popular technique for developing open domain dialogue systems, though they suffer from the \textit{safe response problem}.
Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
Training the generative models with minimal corpus is one of the critical challenges for building open-domain dialogue systems.
Subword ELMo
Embedding from Language Models (ELMo) has shown to be effective for improving many natural language processing (NLP) tasks, and ELMo takes character information to compose word representation to train language models. However, the character is an insufficient and unnatural linguistic unit for word representation. Thus we introduce Embedding from Subword-aware Language Models (ESuLMo) which learns word representation from subwords using unsupervised segmentation over words. We show that ESuLMo can enhance four benchmark NLP tasks more effectively than ELMo, including syntactic dependency parsing, semantic role labeling, implicit discourse relation recognition and textual entailment, which brings a meaningful improvement over ELMo.
Fine-Grained Sentence Functions for Short-Text Conversation
Classification models are trained on this dataset to (i) recognize the sentence function of new data in a large corpus of short-text conversations; (ii) estimate a proper sentence function of the response given a test query.
Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References
Due to its potential applications, open-domain dialogue generation has become popular and achieved remarkable progress in recent years, but sometimes suffers from generic responses.
Unsupervised Rewriter for Multi-Sentence Compression
First, the word graph approach that simply concatenates fragments from multiple sentences may yield non-fluent or ungrammatical compression.
Learning to Abstract for Memory-augmented Conversational Response Generation
In this work, we propose a memory-augmented generative model, which learns to abstract from the training corpus and saves the useful information to the memory to assist the response generation.
Generating Multiple Diverse Responses for Short-Text Conversation
In this paper, we propose a novel response generation model, which considers a set of responses jointly and generates multiple diverse responses simultaneously.
Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method
We observe that in the conversation tasks, each query could have multiple responses, which forms a 1-to-n or m-to-n relationship in the view of the total corpus.
Language Style Transfer from Sentences with Arbitrary Unknown Styles
Then, by recombining the content with the target style, we decode a sentence aligned in the target domain.
Mandatory Leaf Node Prediction in Hierarchical Multilabel Classification
However, while there have been a lot of MLNP methods in hierarchical multiclass classification, performing MLNP in hierarchical multilabel classification is much more difficult.
